Publications

339 / 3,802 publications found.


  •  Hori, C., Hori, T., Lee, T.-Y., Zhang, Z., Harsham, B.A., Sumi, K., Marks, T.K., Hershey, J.R., "Attention-Based Multimodal Fusion for Video Description", IEEE International Conference on Computer Vision (ICCV), DOI: 10.1109/​ICCV.2017.450, October 2017.
    BibTeX TR2017-156 PDF
    • @inproceedings{Hori2017oct,
    • author = {Hori, Chiori and Hori, Takaaki and Lee, Teng-Yok and Zhang, Ziming and Harsham, Bret A. and Sumi, Kazuhiko and Marks, Tim K. and Hershey, John R.},
    • title = {{Attention-Based Multimodal Fusion for Video Description}},
    • booktitle = {IEEE International Conference on Computer Vision (ICCV)},
    • year = 2017,
    • month = oct,
    • doi = {10.1109/ICCV.2017.450},
    • url = {https://www.merl.com/publications/TR2017-156}
    • }
  •  Ochiai, T., Watanabe, S., Katagiri, S., "Does speech enhancement work with end-to-end ASR objectives?: Experimental analysis of multichannel end-to-end ASR", IEEE International Workshop on Machine Learning for Signal Processing (MLSP), DOI: 10.1109/​JSTSP.2017.2764276, October 2017, vol. 11, pp. 1274-1288.
    BibTeX TR2017-139 PDF
    • @inproceedings{Ochiai2017oct,
    • author = {Ochiai, Tsubasa and Watanabe, Shinji and Katagiri, Shigeru},
    • title = {{Does speech enhancement work with end-to-end ASR objectives?: Experimental analysis of multichannel end-to-end ASR}},
    • booktitle = {IEEE International Workshop on Machine Learning for Signal Processing (MLSP)},
    • year = 2017,
    • volume = 11,
    • number = 8,
    • pages = {1274--1288},
    • month = oct,
    • doi = {10.1109/JSTSP.2017.2764276},
    • url = {https://www.merl.com/publications/TR2017-139}
    • }
  •  Ochiai, T., Watanabe, S., Hori, T., Hershey, J.R., Xiao, X., "Unified Architecture for Multichannel End-to-End Speech Recognition with Neural Beamforming", IEEE Journal of Selected Topics in Signal Processing, DOI: 10.1109/​JSTSP.2017.2764276, Vol. 11, No. 8, pp. 1274-1288, October 2017.
    BibTeX TR2017-192 PDF
    • @article{Ochiai2017oct2,
    • author = {Ochiai, Tsubasa and Watanabe, Shinji and Hori, Takaaki and Hershey, John R. and Xiao, Xiong},
    • title = {{Unified Architecture for Multichannel End-to-End Speech Recognition with Neural Beamforming}},
    • journal = {IEEE Journal of Selected Topics in Signal Processing},
    • year = 2017,
    • volume = 11,
    • number = 8,
    • pages = {1274--1288},
    • month = oct,
    • doi = {10.1109/JSTSP.2017.2764276},
    • issn = {1941-0484},
    • url = {https://www.merl.com/publications/TR2017-192}
    • }
  •  Watanabe, S., Hori, T., Kim, S., Hershey, J.R., Hayashi, T., "Hybrid CTC/Attention Architecture for End-to-End Speech Recognition", IEEE Journal of Selected Topics in Signal Processing, DOI: 10.1109/​JSTSP.2017.2763455, Vol. 11, No. 8, pp. 1240-1253, October 2017.
    BibTeX TR2017-190 PDF Video
    • @article{Watanabe2017oct,
    • author = {Watanabe, Shinji and Hori, Takaaki and Kim, Suyoun and Hershey, John R. and Hayashi, Tomoki},
    • title = {{Hybrid CTC/Attention Architecture for End-to-End Speech Recognition}},
    • journal = {IEEE Journal of Selected Topics in Signal Processing},
    • year = 2017,
    • volume = 11,
    • number = 8,
    • pages = {1240--1253},
    • month = oct,
    • doi = {10.1109/JSTSP.2017.2763455},
    • issn = {1941-0484},
    • url = {https://www.merl.com/publications/TR2017-190}
    • }
  •  Magron, P., Le Roux, J., Virtanen, T., "Consistent Anisotropic Wiener Filtering for Audio Source", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), DOI: 10.1109/​WASPAA.2017.8170037, October 2017.
    BibTeX TR2017-151 PDF
    • @inproceedings{Magron2017oct,
    • author = {Magron, Paul and {Le Roux}, Jonathan and Virtanen, Tuomas},
    • title = {{Consistent Anisotropic Wiener Filtering for Audio Source }},
    • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
    • year = 2017,
    • month = oct,
    • doi = {10.1109/WASPAA.2017.8170037},
    • url = {https://www.merl.com/publications/TR2017-151}
    • }
  •  Hori, T., Watanabe, S., Zhang, Y., Chan, W., "Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM", Interspeech, August 2017.
    BibTeX TR2017-132 PDF Video
    • @inproceedings{Hori2017aug,
    • author = {Hori, Takaaki and Watanabe, Shinji and Zhang, Yu and Chan, William},
    • title = {{Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM}},
    • booktitle = {Interspeech},
    • year = 2017,
    • month = aug,
    • url = {https://www.merl.com/publications/TR2017-132}
    • }
  •  Shinozaki, T., Watanabe, S., Mochihashi, D., Neubig, G., "Semi-Supervised Learning of a Pronunciation Dictionary from Disjoint Phonemic Transcripts and Text", Interspeech, August 2017.
    BibTeX TR2017-133 PDF
    • @inproceedings{Shinozaki2017aug,
    • author = {Shinozaki, Takahiro and Watanabe, Shinji and Mochihashi, Daichi and Neubig, Graham},
    • title = {{Semi-Supervised Learning of a Pronunciation Dictionary from Disjoint Phonemic Transcripts and Text}},
    • booktitle = {Interspeech},
    • year = 2017,
    • month = aug,
    • url = {https://www.merl.com/publications/TR2017-133}
    • }
  •  Tachioka, Y., Narita, T., Miura, I., Uramoto, T., Monta, N., Uenohara, S., Furuya, K., Watanabe, S., Le Roux, J., "Coupled initialization of multi-channel non-negative matrix factorization based on spatial and spectral information", Interspeech, August 2017.
    BibTeX TR2017-134 PDF
    • @inproceedings{Tachioka2017aug,
    • author = {Tachioka, Yuuki and Narita, Tomohiro and Miura, Iori and Uramoto, Takanobu and Monta, Natsuki and Uenohara, Shingo and Furuya, Kenichi and Watanabe, Shinji and {Le Roux}, Jonathan},
    • title = {{Coupled initialization of multi-channel non-negative matrix factorization based on spatial and spectral information}},
    • booktitle = {Interspeech},
    • year = 2017,
    • month = aug,
    • url = {https://www.merl.com/publications/TR2017-134}
    • }
  •  Hayashi, T., Watanabe, S., Toda, T., Hori, T., Le Roux, J., Takeda, K., "Duration-Controlled LSTM for Polyphonic Sound Event Detection", IEEE/ACM Transactions on Audio, Speech, and Language Processing, DOI: 10.1109/​TASLP.2017.2740002, Vol. 25, No. 11, August 2017.
    BibTeX TR2017-150 PDF
    • @article{Hayashi2017aug,
    • author = {Hayashi, Tomoki and Watanabe, Shinji and Toda, Tomoki and Hori, Takaaki and {Le Roux}, Jonathan and Takeda, Kazuya},
    • title = {{Duration-Controlled LSTM for Polyphonic Sound Event Detection}},
    • journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    • year = 2017,
    • volume = 25,
    • number = 11,
    • month = aug,
    • doi = {10.1109/TASLP.2017.2740002},
    • issn = {2329-9304},
    • url = {https://www.merl.com/publications/TR2017-150}
    • }
  •  Ochiai, T., Watanabe, S., Hori, T., Hershey, J.R., "Multichannel End-to-end Speech Recognition", International Conference on Machine Learning (ICML), August 2017.
    BibTeX TR2017-107 PDF
    • @inproceedings{Ochiai2017aug,
    • author = {Ochiai, Tsubasa and Watanabe, Shinji and Hori, Takaaki and Hershey, John R.},
    • title = {{Multichannel End-to-end Speech Recognition}},
    • booktitle = {International Conference on Machine Learning (ICML)},
    • year = 2017,
    • month = aug,
    • url = {https://www.merl.com/publications/TR2017-107}
    • }
  •  Hori, T., Watanabe, S., Hershey, J.R., "Joint CTC/attention decoding for end-to-end speech recognition", Association for Computational Linguistics (ACL), DOI: 10.18653/​v1/​P17-1048, July 2017, pp. 518-529.
    BibTeX TR2017-103 PDF Video
    • @inproceedings{Hori2017jul,
    • author = {Hori, Takaaki and Watanabe, Shinji and Hershey, John R.},
    • title = {{Joint CTC/attention decoding for end-to-end speech recognition}},
    • booktitle = {Association for Computational Linguistics (ACL)},
    • year = 2017,
    • pages = {518--529},
    • month = jul,
    • doi = {10.18653/v1/P17-1048},
    • url = {https://www.merl.com/publications/TR2017-103}
    • }
  •  Watanabe, S., Hori, T., Hayashi, T., Kim, S., "End-to-end ASR without using morphological analyzer, pronunciation dictionary and language model", Acoustical Society of Japan Spring Meeting (ASJ), March 2017.
    BibTeX TR2017-021 PDF
    • @inproceedings{Watanabe2017mar2,
    • author = {Watanabe, Shinji and Hori, Takaaki and Hayashi, Tomoki and Kim, Suyoun},
    • title = {{End-to-end ASR without using morphological analyzer, pronunciation dictionary and language model}},
    • booktitle = {Acoustical Society of Japan Spring Meeting (ASJ)},
    • year = 2017,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2017-021}
    • }
  •  Hayashi, T., Watanabe, S., Toda, T., Hori, T., Le Roux, J., Takeda, K., "BLSTM-HMM Hybrid System Combined with Sound Activity Detection Network for Polyphonic Sound Event Detection", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
    BibTeX TR2017-014 PDF
    • @inproceedings{Hayashi2017mar,
    • author = {Hayashi, Tomoki and Watanabe, Shinji and Toda, Tomoki and Hori, Takaaki and {Le Roux}, Jonathan and Takeda, Kazuya},
    • title = {{BLSTM-HMM Hybrid System Combined with Sound Activity Detection Network for Polyphonic Sound Event Detection}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2017,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2017-014}
    • }
  •  Kim, S., Hori, T., Watanabe, S., "Joint CTC- Attention Based End-to-End Speech Recognition Using Multi-task Learning", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
    BibTeX TR2017-016 PDF Video
    • @inproceedings{Kim2017mar,
    • author = {Kim, Suyoun and Hori, Takaaki and Watanabe, Shinji},
    • title = {{Joint CTC- Attention Based End-to-End Speech Recognition Using Multi-task Learning}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2017,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2017-016}
    • }
  •  Luo, Y., Chen, Z., Hershey, J.R., Le Roux, J., Mesgarani, N., "Deep Clustering and Conventional Networks for Music Separation: Strong Together", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
    BibTeX TR2017-010 PDF
    • @inproceedings{Luo2017mar,
    • author = {Luo, Yi and Chen, Zhuo and Hershey, John R. and {Le Roux}, Jonathan and Mesgarani, Nima},
    • title = {{Deep Clustering and Conventional Networks for Music Separation: Strong Together}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2017,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2017-010}
    • }
  •  Meng, Z., Watanabe, S., Hershey, J.R., Erdogan, H., "Deep Long Short-Term Memory Adaptive Beamforming Networks for Multichannel Robust Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
    BibTeX TR2017-012 PDF
    • @inproceedings{Meng2017mar,
    • author = {Meng, Zhong and Watanabe, Shinji and Hershey, John R. and Erdogan, Hakan},
    • title = {{Deep Long Short-Term Memory Adaptive Beamforming Networks for Multichannel Robust Speech Recognition}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2017,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2017-012}
    • }
  •  Watanabe, S., Hori, T., Le Roux, J., Hershey, J.R., "Student-Teacher Network Learning with Enhanced Features", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
    BibTeX TR2017-011 PDF
    • @inproceedings{Watanabe2017mar,
    • author = {Watanabe, Shinji and Hori, Takaaki and {Le Roux}, Jonathan and Hershey, John R.},
    • title = {{Student- Teacher Network Learning with Enhanced Features}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2017,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2017-011}
    • }
  •  Xiao, X., Watanabe, S., Chng, E.S., Li, H., "Beamforming Networks Using Spatial Covariance Features for Far-field Speech Recognition", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)<br /> , DOI: 10.1109/​APSIPA.2016.7820724, December 2016.
    BibTeX TR2016-162 PDF
    • @inproceedings{Xiao2016dec,
    • author = {Xiao, Xiong and Watanabe, Shinji and Chng, Eng Siong and Li, Haizhou},
    • title = {{Beamforming Networks Using Spatial Covariance Features for Far-field Speech Recognition}},
    • booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
      },
    • year = 2016,
    • month = dec,
    • doi = {10.1109/APSIPA.2016.7820724},
    • url = {https://www.merl.com/publications/TR2016-162}
    • }
  •  Hori, T., Wang, H., Hori, C., Watanabe, S., Harsham, B.A., Le Roux, J., Hershey, J.R., Koji, Y., Jing, Y., Zhu, Z., Aikawa, T., "Dialog State Tracking with Attention-based Sequence-to-sequence Learning", IEEE Workshop on Spoken Language Technology (SLT), DOI: 10.1109/​SLT.2016.7846317, December 2016, pp. 552-558.
    BibTeX TR2016-163 PDF
    • @inproceedings{Hori2016dec,
    • author = {Hori, Takaaki and Wang, Hai and Hori, Chiori and Watanabe, Shinji and Harsham, Bret A. and {Le Roux}, Jonathan and Hershey, John R. and Koji, Yusuke and Jing, Yi and Zhu, Zhaocheng and Aikawa, Takeyuki},
    • title = {{Dialog State Tracking with Attention-based Sequence-to-sequence Learning}},
    • booktitle = {IEEE Workshop on Spoken Language Technology (SLT)},
    • year = 2016,
    • pages = {552--558},
    • month = dec,
    • doi = {10.1109/SLT.2016.7846317},
    • url = {https://www.merl.com/publications/TR2016-163}
    • }
  •  Takano, T., Moriya, T., Shinozaki, T., Watanabe, S., Hori, T., Duh, K., "Automated Structure Discovery and Parameter Tuning of Neural Network Language Model Based on Evolution Strategy", IEEE Spoken Language Technology Workshop (SLT), DOI: 10.1109/​SLT.2016.7846334, December 2016.
    BibTeX TR2016-173 PDF
    • @inproceedings{Takano2016dec,
    • author = {Takano, Tomihiro and Moriya, Takafumi and Shinozaki, Takahiro and Watanabe, Shinji and Hori, Takaaki and Duh, Kevin},
    • title = {{Automated Structure Discovery and Parameter Tuning of Neural Network Language Model Based on Evolution Strategy}},
    • booktitle = {IEEE Spoken Language Technology Workshop (SLT)},
    • year = 2016,
    • month = dec,
    • doi = {10.1109/SLT.2016.7846334},
    • url = {https://www.merl.com/publications/TR2016-173}
    • }
  •  Barker, J., Marxer, R., Vincent, E., Watanabe, S., "The Third 'CHIME' Speech Separation and Recognition Challenge: Analysis and Outcomes", Computer Speech & Language, DOI: 10.1016/​j.csl.2016.10.005, December 2016.
    BibTeX TR2016-171 PDF
    • @article{Barker2016dec,
    • author = {Barker, Jon and Marxer, Ricard and Vincent, Emmanuel and Watanabe, Shinji},
    • title = {{The Third 'CHIME' Speech Separation and Recognition Challenge: Analysis and Outcomes}},
    • journal = {Computer Speech \& Language},
    • year = 2016,
    • month = dec,
    • publisher = {Elsevier},
    • doi = {10.1016/j.csl.2016.10.005},
    • url = {https://www.merl.com/publications/TR2016-171}
    • }
  •  Wisdom, S., Powers, T., Hershey, J.R., Le Roux, J., Atlas, L., "Full-Capacity Unitary Recurrent Neural Networks", Advances in Neural Information Processing Systems (NIPS), December 2016.
    BibTeX TR2016-155 PDF
    • @inproceedings{Wisdom2016dec,
    • author = {Wisdom, Scott and Powers, Thomas and Hershey, John R. and {Le Roux}, Jonathan and Atlas, Les},
    • title = {{Full-Capacity Unitary Recurrent Neural Networks}},
    • booktitle = {Advances in Neural Information Processing Systems (NIPS)},
    • year = 2016,
    • month = dec,
    • url = {https://www.merl.com/publications/TR2016-155}
    • }
  •  Vincent, E., Watanabe, S., Nugraha, A.A., Barker, J., Marxer, R., "An analysis of environment, microphone and data simulation mismatches in robust speech recognition", Computer Speech & Language, DOI: 10.1016/​j.csl.2016.11.005, December 2016.
    BibTeX TR2016-172 PDF
    • @article{Vincent2016dec,
    • author = {Vincent, Emmanuel and Watanabe, Shinji and Nugraha, Aditya Arie and Barker, Jon and Marxer, Ricard},
    • title = {{An analysis of environment, microphone and data simulation mismatches in robust speech recognition}},
    • journal = {Computer Speech \& Language},
    • year = 2016,
    • month = dec,
    • publisher = {Elsevier},
    • doi = {10.1016/j.csl.2016.11.005},
    • url = {https://www.merl.com/publications/TR2016-172}
    • }
  •  Tawara, N., Ogawa, T., Watanabe, S., Kobayashi, T., "Nested Gibbs sampling for mixture-of-mixture model and its application to speaker clustering", APSIPA Transactions on Signal and Information Processing, DOI: 10.1017/​ATSIP.2016.15, Vol. 5, October 2016.
    BibTeX TR2016-138 PDF
    • @article{Tawara2016oct,
    • author = {Tawara, Naohiro and Ogawa, Tetsuji and Watanabe, Shinji and Kobayashi, Tetsunori},
    • title = {{Nested Gibbs sampling for mixture-of-mixture model and its application to speaker clustering}},
    • journal = {APSIPA Transactions on Signal and Information Processing},
    • year = 2016,
    • volume = 5,
    • month = oct,
    • doi = {10.1017/ATSIP.2016.15},
    • url = {https://www.merl.com/publications/TR2016-138}
    • }
  •  Delcroix, M., Watanabe, S., "Recent Advances in Distant Speech Recognition," Tech. Rep. TR2016-115, Interspeech Tutorials, September 2016.
    BibTeX TR2016-115 PDF
    • @techreport{Delcroix2016sep,
    • author = {Delcroix, Marc and Watanabe, Shinji},
    • title = {{Recent Advances in Distant Speech Recognition}},
    • booktitle = {Interspeech Tutorials},
    • institution = {Interspeech},
    • year = 2016,
    • month = sep,
    • url = {https://www.merl.com/publications/TR2016-115}
    • }